Memory family: additive trace accumulation

Read the equation

The update stores an increment equal to 0.02 times the sum of normalized input and utility. Repeated updates accumulate their history in a single scalar, so different histories with the same accumulated sum are indistinguishable. No forgetting factor appears in this individual rule.

Terms & definitions

How it works

Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.

Assumptions & limits

Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.

Original context

## 3.14 Family 13: Memory Trace (Zecher)

```
f₁₃(x) = x + 0.02 · (dx_norm + utility)
```

**Equation Type**: Trace accumulation: x'_i = Σ f_i : dΩ

**Explanation**: Slowly accumulates both change and utility signals, creating persistent memory traces. Named "Zecher" (Hebrew for "memory").

## 3.15 Family 14: Decisive Action / Policy

```
f₁₄(x) = x + 0.15 · softsign(utility) - 0.05 · ed_error
```

**Equation Type**: Policy gradient: π(a|s)

**Explanation**: Generates action outputs by amplifying utility signals and suppressing errors. The larger positive coefficient on utility makes this an action-oriented family.

## 3.16 Family 15: Global Coherence (Kehillah)

```
f₁₅(x) = x + (φ - 1) · 0.01 · (stability - x)

f₁₃(x) = x + 0.02 · (dx_norm + utility)

Related builds